Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to membership or association

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    antMatchers
    -0.65
    Geplaatst
    -0.61
     חיצוניים
    -0.60
    BufferException
    -0.60
     regra
    -0.60
     equator
    -0.60
     imageNamed
    -0.60
    出版年
    -0.59
     مشين
    -0.58
     Bany
    -0.57
    POSITIVE LOGITS
     Jefus
    0.91
     ſche
    0.75
     Majefty
    0.75
     Madsen
    0.74
     leaſt
    0.74
     ſon
    0.72
     Monfieur
    0.72
    kuuta
    0.72
     ſen
    0.69
     orec
    0.69
    Act Density 0.016%

    No Known Activations